\n",
"\n",
""
]
},
"metadata": {}
}
]
},
{
"cell_type": "markdown",
"source": [
"Легко видеть, что зависимости от этажа нет"
],
"metadata": {
"id": "kIk_6i37lBjx"
}
},
{
"cell_type": "markdown",
"source": [
"Интересно посмотреть, на распределения по object_type. В задании описания данного параметра нет. Узнаем, как он влияет на цену"
],
"metadata": {
"id": "GLknxc-YtJGy"
}
},
{
"cell_type": "code",
"source": [
"plt.hist(df_stripped.query(\"object_type == 1\").price, bins=100, alpha=0.5, label=\"object_type = 1\")\n",
"plt.hist(df_stripped.query(\"object_type == 11\").price, bins=100, alpha=0.5, label=\"object_type = 11\")\n",
"plt.xlabel(\"price\")\n",
"plt.ylabel(\"count\")\n",
"plt.legend();"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 449
},
"id": "KOBucnRCsTHa",
"outputId": "ac011f02-e60a-41e3-97ee-e6b1d1c43a64"
},
"execution_count": null,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"image/png": "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\n"
},
"metadata": {}
}
]
},
{
"cell_type": "markdown",
"source": [
"Распределения близки друг к другу. Имеет смысл проводить более подробное исследование + выяснить за что отвечает данный параметр"
],
"metadata": {
"id": "174t7enz343c"
}
},
{
"cell_type": "markdown",
"source": [
"**8. [2 балла] Какие выводы можно сделать, по получившимся результатам? Какие переменные можно было бы использовать для предсказания стоимости объекта недвижимости? Какие гипотезы проверили бы еще с помощью первоначального анализа данных?**"
],
"metadata": {
"id": "WVNoGlMhmyX5"
}
},
{
"cell_type": "markdown",
"source": [
"Удалось найти зависимость цены(на примере Питера) от расположения. Однако по номеру этажа и площади зависимость обнаружить не удалось.\n",
"\n",
"Переменные, которые можно было бы использовать для предсказания:\n",
"* id региона\n",
"* площадь\n",
"* жилая площадь\n",
"* координаты(широта, долгота). Можно смотреть на цены близжайших объектов\n",
"\n",
"Гипотезы для проверки:\n",
"* Дата продажи вляет на цену объекта недвижимости\n",
"* цена на объекты в некоторых районах зависит от object_type. Если, например это жилой и нежилой фонд, то, условно, возле парка цены на жилые помещения выше, чем цены на склады и, наоборот возле жд развязки"
],
"metadata": {
"id": "5l61QzsqnJG3"
}
},
{
"cell_type": "markdown",
"source": [
"**9. [2 балла, бонус] Вставьте картинку, описывающую ваш опыт от работы с `pandas`. Вставить картинку можно добавив тектовый блок и выбрав в нем загрузку(вставку) картинки**"
],
"metadata": {
"id": "f5Xuxmf0m3is"
}
},
{
"cell_type": "markdown",
"source": [
""
],
"metadata": {
"id": "TMAqlP-1nO-6"
}
},
{
"cell_type": "code",
"source": [],
"metadata": {
"id": "pRql0Yi458bq"
},
"execution_count": null,
"outputs": []
}
]
}